Vertex AI Workbench - Quick Deploy

We have collaborated with Google Cloud to simplify the deployment of Jupyter Notebooks, from a dozen complex steps to a single click. Now you can launch frameworks, SDKs and models directly to Google Cloud’s Vertex AI Workbench, a new managed Jupyter Notebook service.

The quick deploy feature automatically sets up the Vertex AI instance with an optimal configuration, preloads the dependencies, runs the software from NGC, and allows you to focus on development rather than setup.

AI Tools Included in this Collection

NVIDIA releases a new version every month for many of the NVIDIA built AI software, updated with optimized libraries, delivering higher training and inference performance on the same GPU-powered system.

• PyTorch: An optimized tensor library for deep learning using GPUs and CPUs.
• TensorFlow: A deep learning framework that provides comprehensive tools and libraries in a flexible architecture allowing easy deployment across a variety of platforms and devices.
• Merlin: a framework for accelerating the entire recommender systems pipeline on the GPU
• RAPIDS: Accelerates end-to-end data science and analytics pipelines entirely on GPUs.
• Example Notebooks: Computer vision, Speech, and recommender system example for you to get started. Also see the Models page for the full list of models across vision, speech, healthcare, and more.

Usage

To use this collection - follow these steps:

1. Navigate to the entities tab
2. Choose the entity you want to deploy
3. Select deploy in the top right of the NGC UI
4. Launch the asset in Google Cloud

You can also follow step-by-step instructions in these blogs to build and deploy Machine Learning and Computer Vision applications using Quick Deploy.